© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 12178
    Prev
    Next
    INDEX
    Explanations

    proper names, especially the name "Maurice"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those named Maurice and Mara

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cyclopedia
    -0.82
    rophe
    -0.81
    urgy
    -0.79
    ebook
    -0.78
    belt
    -0.74
    wrapper
    -0.74
    packs
    -0.73
    eled
    -0.72
    eners
    -0.71
    olics
    -0.70
    POSITIVE LOGITS
     Maurice
    0.83
     streng
    0.75
     livest
    0.74
     Maur
    0.73
    theless
    0.73
     Blackburn
    0.69
    HAEL
    0.69
    channelAvailability
    0.68
    angelo
    0.66
    uchin
    0.65
    Activations Density 0.020%

    No Known Activations